UPSTREAM: cpufreq: schedutil: Make iowait boost more energy efficient

Currently the iowait_boost feature in schedutil makes the frequency go
to max on iowait wakeups.  This feature was added to handle a case that
Peter described where the throughput of operations involving continuous
I/O requests [1] is reduced due to running at a lower frequency, however
the lower throughput itself causes utilization to be low and hence
causing frequency to be low hence its "stuck".

Instead of going to max, its also possible to achieve the same effect by
ramping up to max if there are repeated in_iowait wakeups happening.
This patch is an attempt to do that. We start from a lower frequency
(policy->min) and double the boost for every consecutive iowait update
until we reach the maximum iowait boost frequency (iowait_boost_max).

I ran a synthetic test (continuous O_DIRECT writes in a loop) on an x86
machine with intel_pstate in passive mode using schedutil. In this test
the iowait_boost value ramped from 800MHz to 4GHz in 60ms. The patch
achieves the desired improved throughput as the existing behavior.

[1] https://patchwork.kernel.org/patch/9735885/

Change-Id: I4a018434a50f4ca29ec15b03465f6dc212e54423
Cc: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Suggested-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Joel Fernandes <joelaf@google.com>

1 files changed, 32 insertions, 6 deletions

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index e12309c1b07b..f6b95ca15023 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -64,6 +64,7 @@ struct sugov_cpu {
 	struct update_util_data update_util;
 	struct sugov_policy *sg_policy;
 
+	bool iowait_boost_pending;
 	unsigned long iowait_boost;
 	unsigned long iowait_boost_max;
 	u64 last_update;
@@ -224,30 +225,54 @@ static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
 				   unsigned int flags)
 {
 	if (flags & SCHED_CPUFREQ_IOWAIT) {
-		sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
+		if (sg_cpu->iowait_boost_pending)
+			return;
+
+		sg_cpu->iowait_boost_pending = true;
+
+		if (sg_cpu->iowait_boost) {
+			sg_cpu->iowait_boost <<= 1;
+			if (sg_cpu->iowait_boost > sg_cpu->iowait_boost_max)
+				sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
+		} else {
+			sg_cpu->iowait_boost = sg_cpu->sg_policy->policy->min;
+		}
 	} else if (sg_cpu->iowait_boost) {
 		s64 delta_ns = time - sg_cpu->last_update;
 
 		/* Clear iowait_boost if the CPU apprears to have been idle. */
-		if (delta_ns > TICK_NSEC)
+		if (delta_ns > TICK_NSEC) {
 			sg_cpu->iowait_boost = 0;
+			sg_cpu->iowait_boost_pending = false;
+		}
 	}
 }
 
 static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
 			       unsigned long *max)
 {
-	unsigned long boost_util = sg_cpu->iowait_boost;
-	unsigned long boost_max = sg_cpu->iowait_boost_max;
+	unsigned long boost_util, boost_max;
 
-	if (!boost_util)
+	if (!sg_cpu->iowait_boost)
 		return;
 
+	if (sg_cpu->iowait_boost_pending) {
+		sg_cpu->iowait_boost_pending = false;
+	} else {
+		sg_cpu->iowait_boost >>= 1;
+		if (sg_cpu->iowait_boost < sg_cpu->sg_policy->policy->min) {
+			sg_cpu->iowait_boost = 0;
+			return;
+		}
+	}
+
+	boost_util = sg_cpu->iowait_boost;
+	boost_max = sg_cpu->iowait_boost_max;
+
 	if (*util * boost_max < *max * boost_util) {
 		*util = boost_util;
 		*max = boost_max;
 	}
-	sg_cpu->iowait_boost >>= 1;
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
@@ -320,6 +345,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu)
 		delta_ns = last_freq_update_time - j_sg_cpu->last_update;
 		if (delta_ns > TICK_NSEC) {
 			j_sg_cpu->iowait_boost = 0;
+			j_sg_cpu->iowait_boost_pending = false;
 			continue;
 		}
 		if (j_sg_cpu->flags & SCHED_CPUFREQ_DL)